在過去的金融文獻中，有大量的資產定價的文獻。許多學者努力研究影響股票價 格的因素，如動量、流動性和其他風險因素。對於投資者來說，基本面、新聞、政治 等也會影響股市的走勢。因此，股票價格是很難預測的，因為價格背後的機制是複雜 的且可能涉及多層面的驅動因素。本研究使用近年來文獻上很受關注的「注意力-長 短期記憶」(Attention-LSTM) 混合模型，並探討此混合模型在預測未來股票價格走勢 方面是否比傳統的 LSTM 模型做得更好。本文研究了 1980 年至 2021 年 S&P500 指數 的成分股資料。按市值排序，每週選擇市值最大的 50 檔股票，並預測它們在下周的 報酬率。本研究發現從上述 50 檔股票中選出 5 檔被預測在下周會產生最大正報酬的 股票，並持有到下周。這個過程一直重複到我們研究期結束。我們的實證結果顯示， 「注意力-長短期記憶」混合模型在預測美國股票的周回報率方面更加準確，並且超 過了標準普爾 500 指數的基準指數。最後，使用可解釋 AI- Shapley value 的方式對注 意力-長短期記憶」(Attention-LSTM) 混合模型的驅動因子進行解釋，發現財務上的 「動能因子」與「流動性」因子仍然是影響股價的主要因子。

In the past financial literature, there is a vast amount of literature in asset pricing. Many scholars have made effort to study the factors that affect stock price, such as momentum, liquidity, and other risk factors. For investors, fundamentals, news, politics, etc. also affect the movement of stock market. As a result, stock prices are very difficult to predict because the mechanics behind the prices are complex which might involve multi-dimensions of driving factors. This study uses the popular Attention-LSTM hybrid model and aims to explore whether the hybrid model will do better than the traditional LSTM model in predicting the future stock price movement. We study the data on the constituent stocks in the S&P500 index from 1980 to 2021. sorting them by market capitalization. The top 50 stocks by market capitalization are selected weekly and their returns in the next week are predicted. We form and hold a portfolio of 5 out of the 50 stocks above which are predicted to generate largest positive returns in the next week. The process is repeated until the end of our study period. Our empirical results show that the Attention -LSTM hybrid model is more accurate in predicting US stocks weekly returns and outperforms the S&P 500 benchmark index. Finally, we use Shapely value to explain the drivers of Attention- LSTM model and find that the financial "momentum factor" and "liquidity factor " are still the main factors affecting the stock price.

Abe, M., & Nakayama, H. (2018, June). Deep learning for forecasting stock returns in the cross-section. In Pacific-Asia conference on knowledge discovery and data mining (pp. 273-284). Springer, Cham.
Alberg, J., & Lipton, Z. C. (2017). Improving factor-based quantitative investing by forecasting company fundamentals. arXiv preprint arXiv:1711.04837.
Amihud, Y., & Mendelson, H. (1989). The effects of beta, bid‐ask spread, residual risk, and size on stock returns. The Journal of Finance, 44(2), 479-486.
Amihud, Y. (2002). Illiquidity and stock returns: cross-section and time-series effects. Journal of financial markets, 5(1), 31-56.
Bali, T. G., Cakici, N., & Whitelaw, R. F. (2011). Maxing out: Stocks as lotteries and the cross-section of expected returns. Journal of financial economics, 99(2), 427-446.
Banz, R. W. (1981). The relationship between return and market value of common stocks. Journal of financial economics, 9(1), 3-18.
Bluwstein, K., Buckmann, M., Joseph, A., Kapadia, S., & Simsek, Ö . (2021). Credit growth, the yield curve and financial crisis prediction: evidence from a machine learning approach.
Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of econometrics, 31(3), 307-327.
Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.
Casabianca et al.(2019)An Early Warning System for banking crises: From regression-based analysis to machine learning techniques.Working Papers No.235
Chen, S., & Ge, L. (2019). Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction. Quantitative Finance, 19(9), 1507-1515.
Collins, J. (1957). How to Study the Behavior of Bank Stocks. The Analysts Journal, 13, 109-113.
Chong, E., Han, C., & Park, F. C. (2017). Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies. Expert Systems with Applications, 83, 187-205.
Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473.
Chordia, T., Subrahmanyam, A., & Anshuman, V. R. (2001). Trading activity and expected stock returns. Journal of financial Economics, 59(1), 3-32.
Datar, V. T., Naik, N. Y., & Radcliffe, R. (1998). Liquidity and stock returns: An alternative test. Journal of financial markets, 1(2), 203-219.
Eldomiaty, T., Saeed, Y., Hammam, R., & AboulSoud, S. (2019). The associations between stock prices, inflation rates, interest rates are still persistent: Empirical evidence from stock duration model. Journal of Economics, Finance and Administrative Science, 25(49), 149-161
Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica: Journal of the econometric society, 987-1007.
Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica: Journal of the econometric society, 987-1007.
Fama, E. F., & MacBeth, J. D. (1973). Risk, return, and equilibrium: Empirical tests. Journal of political economy, 81(3), 607-636.
Fallahgoul, H., Franstianto, V., & Lin, X. (2020). Asset Pricing with Neural Networks: A Variable Significant Test. Available at SSRN 3889777.
Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669.
Gao, J. (2021). Research on Stock Price Forecast Based on ARIMA-GARCH Model. In
E3S Web of Conferences (Vol. 292, p. 02030). EDP Sciences.
Green, J., Hand, J., & Zhang, F. (2014). The remarkable multidimensionality in the cross section of expected US stock returns. Available at SSRN, 2262374.
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The
Review of Financial Studies, 33(5), 2223-2273.
Hou, K., Xue, C., & Zhang, L. (2020). Replicating anomalies. The Review of Financial
Studies, 33(5), 2019-2133.
Huang, Y., Capretz, L. F., & Ho, D. (2021, December). Machine learning for stock
prediction based on fundamental analysis. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 01-10). IEEE.
Jegadeesh, N. (1990). Evidence of predictable behavior of security returns. The Journal of finance, 45(3), 881-898.
Jegadeesh, N., & Titman, S. (1993). Returns to buying winners and selling losers: Implications for stock market efficiency. The Journal of finance, 48(1), 65-91.
Liu, L., Chen, C., & Wang, B. (2022). Predicting financial crises with machine learning methods. Journal of Forecasting.
Liu, W. (2006). A liquidity-augmented capital asset pricing model. Journal of financial Economics, 82(3), 631-671.
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30.
Moskowitz, T. J., & Grinblatt, M. (1999). Do industries explain momentum? The Journal of finance, 54(4), 1249-1290.
Pearson, K. (1901). LIII. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin philosophical magazine and journal of science, 2(11), 559-572.
Rapach, D. E., Strauss, J. K., & Zhou, G. (2013). International stock return predictability: What is the role of the United States? The Journal of Finance, 68(4), 1633-1662.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016, August). " Why should i trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135-1144).
Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65(6), 386.
Sattayatham, P., Sopipan, N., & Premanode, B. (2012). Forecasting volatility and price of the SET50 index using the Markov regime switching. Procedia Economics and Finance,2, 265-274.
Shapley, L. S. (1953). Stochastic games. Proceedings of the national academy of sciences, 39(10), 1095-1100.
Shao, B., Yan, Y., & Zeng, H. (2022). VMD-WSLSTM Load Prediction Model Based on Shapley Values. Energies, 15(2), 487.
Shi, Z., Hu, Y., Mo, G., & Wu, J. (2022). Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction. arXiv preprint arXiv:2204.02623.
Strumbelj, E., & Kononenko, I. (2010). An efficient explanation of individual classifications using game theory. The Journal of Machine Learning Research, 11
Sukesti, F., Ghozali, I., Fuad, F. U. A. D., Almasyhari, A. K., & Nurcahyono.(2021). Factors affecting the stock price: The role of firm performance. The Journal of Asian Finance, Economics, and Business, 8(2), 165-173.
Tandon, K., & Malhotra, N. (2013). Determinants of stock prices: Empirical evidence from NSE 100 companies. International Journal of Research in Management & Technology, 3(3), 2249-9563.
Tiffin, M. A. J. (2019). Machine learning and causality: The impact of financial crises on growth. International Monetary Fund.
Vijh, M., Chandola, D., Tikkiwal, V. A., & Kumar, A. (2020). Stock closing price prediction using machine learning techniques. Procedia Computer Science, 167, 599-606. Zou,Z., & Qu, Z. (2020). Using LSTM in Stock prediction and Quantitative Trading. CS230: Deep Learning, Winter.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
Yan, H., & Ouyang, H. (2018). Financial time series prediction based on deep learning. Wireless Personal Communications, 102(2), 683-700.
Yuqing Dai, Yuning Zhang (2013). Machine Learning in Stock Price Trend Forecasting. Stanford University
Zang, H., Xu, R., Cheng, L., Ding, T., Liu, L., Wei, Z., & Sun, G. (2021). Residential load forecasting based on LSTM fusing self-attention mechanism with pooling. Energy, 229.
Zhang, T., Zheng, X. Q., & Liu, M. X. (2021). Multiscale attention-based LSTM for ship motion prediction. Ocean Engineering, 230, 109066.
Zhang, X., Liu, S., & Zheng, X. (2021). Stock price movement prediction based on a deep factorization machine and the attention mechanism. Mathematics, 9(8), 800.
Zou,Z., & Qu, Z. (2020). Using LSTM in Stock prediction and Quantitative Trading. CS230: Deep Learning, Winter.